Business impact

<aside> 💡

The problem: Call recordings sat in Google Sheets as audio links, and the team could only manually listen to a fraction of them — issues, sentiment, and basic stats depended on whatever calls someone had time to review.

What it looked like before: No single place held transcripts, sentiment, or tags together, and pulling analytics for a specific period meant listening back through calls by hand — something that simply didn't scale as call volume grew.

What we built: An automated pipeline that transcribes every call, detects sentiment, extracts key signals, and stores it all in a searchable table — plus a chat assistant that answers analytics questions like "share of negative calls last week" on demand.

Result: Up to 100 calls a day now get processed without manual review, call-quality analysis time dropped by about 90%, and the team saves roughly 8-12 hours of manual work per week. Analytics answers that used to require digging now come back in 10-15 seconds.

</aside>

An automated system for call transcription, sentiment detection, and analytics built with n8n and LLMs.

Project details

Context:

• Business/industry: Sales / Support / Contact Center
• Current process: Call recordings were stored in Google Sheets as links to audio files. The team manually listened to a portion of the calls, noted issues, and collected basic statistics.

Problem:

• Manual call analysis took too much time and did not scale as call volume increased.
• There was no single place to store transcripts, sentiment, tags, metrics, and reports.
• It was not possible to quickly identify negative calls or build analytics for a specific period without manual work.

Solution

<aside> 🧠

The AI call analytics system built with n8n automatically processes audio, generates transcripts, detects sentiment, extracts insights, and stores the results in a table for reporting and search. Tools used: n8n, LLM, Google Sheets, AI transcription and analysis tools.

</aside>

Solution logic:

1. Audio links are read from Google Sheets.